#define guest_walker guest_walker64
#define FNAME(name) paging##64_##name
#define PT_BASE_ADDR_MASK PT64_BASE_ADDR_MASK
- #define PT_DIR_BASE_ADDR_MASK PT64_DIR_BASE_ADDR_MASK
+ #define PT_LVL_ADDR_MASK(lvl) PT64_LVL_ADDR_MASK(lvl)
+ #define PT_LVL_OFFSET_MASK(lvl) PT64_LVL_OFFSET_MASK(lvl)
#define PT_INDEX(addr, level) PT64_INDEX(addr, level)
#define PT_LEVEL_MASK(level) PT64_LEVEL_MASK(level)
#define PT_LEVEL_BITS PT64_LEVEL_BITS
#define guest_walker guest_walker32
#define FNAME(name) paging##32_##name
#define PT_BASE_ADDR_MASK PT32_BASE_ADDR_MASK
- #define PT_DIR_BASE_ADDR_MASK PT32_DIR_BASE_ADDR_MASK
+ #define PT_LVL_ADDR_MASK(lvl) PT32_LVL_ADDR_MASK(lvl)
+ #define PT_LVL_OFFSET_MASK(lvl) PT32_LVL_OFFSET_MASK(lvl)
#define PT_INDEX(addr, level) PT32_INDEX(addr, level)
#define PT_LEVEL_MASK(level) PT32_LEVEL_MASK(level)
#define PT_LEVEL_BITS PT32_LEVEL_BITS
#error Invalid PTTYPE value
#endif
-#define gpte_to_gfn FNAME(gpte_to_gfn)
-#define gpte_to_gfn_pde FNAME(gpte_to_gfn_pde)
+#define gpte_to_gfn_lvl FNAME(gpte_to_gfn_lvl)
+#define gpte_to_gfn(pte) gpte_to_gfn_lvl((pte), PT_PAGE_TABLE_LEVEL)
/*
* The guest_walker structure emulates the behavior of the hardware page
u32 error_code;
};
-static gfn_t gpte_to_gfn(pt_element_t gpte)
+static gfn_t gpte_to_gfn_lvl(pt_element_t gpte, int lvl)
{
- return (gpte & PT_BASE_ADDR_MASK) >> PAGE_SHIFT;
-}
-
-static gfn_t gpte_to_gfn_pde(pt_element_t gpte)
-{
- return (gpte & PT_DIR_BASE_ADDR_MASK) >> PAGE_SHIFT;
+ return (gpte & PT_LVL_ADDR_MASK(lvl)) >> PAGE_SHIFT;
}
static bool FNAME(cmpxchg_gpte)(struct kvm *kvm,
gpa_t pte_gpa;
int rsvd_fault = 0;
- pgprintk("%s: addr %lx\n", __func__, addr);
+ trace_kvm_mmu_pagetable_walk(addr, write_fault, user_fault,
+ fetch_fault);
walk:
walker->level = vcpu->arch.mmu.root_level;
pte = vcpu->arch.cr3;
#if PTTYPE == 64
if (!is_long_mode(vcpu)) {
pte = kvm_pdptr_read(vcpu, (addr >> 30) & 3);
+ trace_kvm_mmu_paging_element(pte, walker->level);
if (!is_present_gpte(pte))
goto not_present;
--walker->level;
pte_gpa += index * sizeof(pt_element_t);
walker->table_gfn[walker->level - 1] = table_gfn;
walker->pte_gpa[walker->level - 1] = pte_gpa;
- pgprintk("%s: table_gfn[%d] %lx\n", __func__,
- walker->level - 1, table_gfn);
- kvm_read_guest(vcpu->kvm, pte_gpa, &pte, sizeof(pte));
+ if (kvm_read_guest(vcpu->kvm, pte_gpa, &pte, sizeof(pte)))
+ goto not_present;
+
+ trace_kvm_mmu_paging_element(pte, walker->level);
if (!is_present_gpte(pte))
goto not_present;
if (rsvd_fault)
goto access_error;
- if (write_fault && !is_writeble_pte(pte))
+ if (write_fault && !is_writable_pte(pte))
if (user_fault || is_write_protection(vcpu))
goto access_error;
goto access_error;
#if PTTYPE == 64
- if (fetch_fault && is_nx(vcpu) && (pte & PT64_NX_MASK))
+ if (fetch_fault && (pte & PT64_NX_MASK))
goto access_error;
#endif
if (!(pte & PT_ACCESSED_MASK)) {
+ trace_kvm_mmu_set_accessed_bit(table_gfn, index,
+ sizeof(pte));
mark_page_dirty(vcpu->kvm, table_gfn);
if (FNAME(cmpxchg_gpte)(vcpu->kvm, table_gfn,
index, pte, pte|PT_ACCESSED_MASK))
walker->ptes[walker->level - 1] = pte;
- if (walker->level == PT_PAGE_TABLE_LEVEL) {
- walker->gfn = gpte_to_gfn(pte);
- break;
- }
-
- if (walker->level == PT_DIRECTORY_LEVEL
- && (pte & PT_PAGE_SIZE_MASK)
- && (PTTYPE == 64 || is_pse(vcpu))) {
- walker->gfn = gpte_to_gfn_pde(pte);
- walker->gfn += PT_INDEX(addr, PT_PAGE_TABLE_LEVEL);
- if (PTTYPE == 32 && is_cpuid_PSE36())
+ if ((walker->level == PT_PAGE_TABLE_LEVEL) ||
+ ((walker->level == PT_DIRECTORY_LEVEL) &&
+ is_large_pte(pte) &&
+ (PTTYPE == 64 || is_pse(vcpu))) ||
+ ((walker->level == PT_PDPE_LEVEL) &&
+ is_large_pte(pte) &&
+ is_long_mode(vcpu))) {
+ int lvl = walker->level;
+
+ walker->gfn = gpte_to_gfn_lvl(pte, lvl);
+ walker->gfn += (addr & PT_LVL_OFFSET_MASK(lvl))
+ >> PAGE_SHIFT;
+
+ if (PTTYPE == 32 &&
+ walker->level == PT_DIRECTORY_LEVEL &&
+ is_cpuid_PSE36())
walker->gfn += pse36_gfn_delta(pte);
+
break;
}
if (write_fault && !is_dirty_gpte(pte)) {
bool ret;
+ trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte));
mark_page_dirty(vcpu->kvm, table_gfn);
ret = FNAME(cmpxchg_gpte)(vcpu->kvm, table_gfn, index, pte,
pte|PT_DIRTY_MASK);
walker->error_code |= PFERR_FETCH_MASK;
if (rsvd_fault)
walker->error_code |= PFERR_RSVD_MASK;
+ trace_kvm_mmu_walker_error(walker->error_code);
return 0;
}
pt_element_t gpte;
unsigned pte_access;
pfn_t pfn;
- int largepage = vcpu->arch.update_pte.largepage;
+ u64 new_spte;
gpte = *(const pt_element_t *)pte;
if (~gpte & (PT_PRESENT_MASK | PT_ACCESSED_MASK)) {
- if (!is_present_gpte(gpte))
- __set_spte(spte, shadow_notrap_nonpresent_pte);
+ if (!is_present_gpte(gpte)) {
+ if (page->unsync)
+ new_spte = shadow_trap_nonpresent_pte;
+ else
+ new_spte = shadow_notrap_nonpresent_pte;
+ __set_spte(spte, new_spte);
+ }
return;
}
pgprintk("%s: gpte %llx spte %p\n", __func__, (u64)gpte, spte);
if (mmu_notifier_retry(vcpu, vcpu->arch.update_pte.mmu_seq))
return;
kvm_get_pfn(pfn);
+ /*
+ * we call mmu_set_spte() with reset_host_protection = true beacuse that
+ * vcpu->arch.update_pte.pfn was fetched from get_user_pages(write = 1).
+ */
mmu_set_spte(vcpu, spte, page->role.access, pte_access, 0, 0,
- gpte & PT_DIRTY_MASK, NULL, largepage,
- gpte_to_gfn(gpte), pfn, true);
+ gpte & PT_DIRTY_MASK, NULL, PT_PAGE_TABLE_LEVEL,
+ gpte_to_gfn(gpte), pfn, true, true);
}
/*
*/
static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
struct guest_walker *gw,
- int user_fault, int write_fault, int largepage,
+ int user_fault, int write_fault, int hlevel,
int *ptwrite, pfn_t pfn)
{
unsigned access = gw->pt_access;
for_each_shadow_entry(vcpu, addr, iterator) {
level = iterator.level;
sptep = iterator.sptep;
- if (level == PT_PAGE_TABLE_LEVEL
- || (largepage && level == PT_DIRECTORY_LEVEL)) {
+ if (iterator.level == hlevel) {
mmu_set_spte(vcpu, sptep, access,
gw->pte_access & access,
user_fault, write_fault,
gw->ptes[gw->level-1] & PT_DIRTY_MASK,
- ptwrite, largepage,
- gw->gfn, pfn, false);
+ ptwrite, level,
+ gw->gfn, pfn, false, true);
break;
}
kvm_flush_remote_tlbs(vcpu->kvm);
}
- if (level == PT_DIRECTORY_LEVEL
- && gw->level == PT_DIRECTORY_LEVEL) {
+ if (level <= gw->level) {
+ int delta = level - gw->level + 1;
direct = 1;
- if (!is_dirty_gpte(gw->ptes[level - 1]))
+ if (!is_dirty_gpte(gw->ptes[level - delta]))
access &= ~ACC_WRITE_MASK;
- table_gfn = gpte_to_gfn(gw->ptes[level - 1]);
+ table_gfn = gpte_to_gfn(gw->ptes[level - delta]);
+ /* advance table_gfn when emulating 1gb pages with 4k */
+ if (delta == 0)
+ table_gfn += PT_INDEX(addr, level);
} else {
direct = 0;
table_gfn = gw->table_gfn[level - 2];
int write_pt = 0;
int r;
pfn_t pfn;
- int largepage = 0;
+ int level = PT_PAGE_TABLE_LEVEL;
unsigned long mmu_seq;
pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code);
return 0;
}
- if (walker.level == PT_DIRECTORY_LEVEL) {
- gfn_t large_gfn;
- large_gfn = walker.gfn & ~(KVM_PAGES_PER_HPAGE-1);
- if (is_largepage_backed(vcpu, large_gfn)) {
- walker.gfn = large_gfn;
- largepage = 1;
- }
+ if (walker.level >= PT_DIRECTORY_LEVEL) {
+ level = min(walker.level, mapping_level(vcpu, walker.gfn));
+ walker.gfn = walker.gfn & ~(KVM_PAGES_PER_HPAGE(level) - 1);
}
+
mmu_seq = vcpu->kvm->mmu_notifier_seq;
smp_rmb();
pfn = gfn_to_pfn(vcpu->kvm, walker.gfn);
goto out_unlock;
kvm_mmu_free_some_pages(vcpu);
sptep = FNAME(fetch)(vcpu, addr, &walker, user_fault, write_fault,
- largepage, &write_pt, pfn);
-
+ level, &write_pt, pfn);
pgprintk("%s: shadow pte %p %llx ptwrite %d\n", __func__,
sptep, *sptep, write_pt);
static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
{
struct kvm_shadow_walk_iterator iterator;
- pt_element_t gpte;
gpa_t pte_gpa = -1;
int level;
u64 *sptep;
level = iterator.level;
sptep = iterator.sptep;
- /* FIXME: properly handle invlpg on large guest pages */
- if (level == PT_PAGE_TABLE_LEVEL ||
- ((level == PT_DIRECTORY_LEVEL) && is_large_pte(*sptep))) {
+ if (level == PT_PAGE_TABLE_LEVEL ||
+ ((level == PT_DIRECTORY_LEVEL && is_large_pte(*sptep))) ||
+ ((level == PT_PDPE_LEVEL && is_large_pte(*sptep)))) {
struct kvm_mmu_page *sp = page_header(__pa(sptep));
+ int offset, shift;
- pte_gpa = (sp->gfn << PAGE_SHIFT);
+ shift = PAGE_SHIFT -
+ (PT_LEVEL_BITS - PT64_LEVEL_BITS) * level;
+ offset = sp->role.quadrant << shift;
+
+ pte_gpa = (sp->gfn << PAGE_SHIFT) + offset;
pte_gpa += (sptep - sp->spt) * sizeof(pt_element_t);
if (is_shadow_present_pte(*sptep)) {
if (need_flush)
kvm_flush_remote_tlbs(vcpu->kvm);
+
+ atomic_inc(&vcpu->kvm->arch.invlpg_counter);
+
spin_unlock(&vcpu->kvm->mmu_lock);
if (pte_gpa == -1)
return;
- if (kvm_read_guest_atomic(vcpu->kvm, pte_gpa, &gpte,
- sizeof(pt_element_t)))
+
+ if (mmu_topup_memory_caches(vcpu))
return;
- if (is_present_gpte(gpte) && (gpte & PT_ACCESSED_MASK)) {
- if (mmu_topup_memory_caches(vcpu))
- return;
- kvm_mmu_pte_write(vcpu, pte_gpa, (const u8 *)&gpte,
- sizeof(pt_element_t), 0);
- }
+ kvm_mmu_pte_write(vcpu, pte_gpa, NULL, sizeof(pt_element_t), 0);
}
-static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr)
+static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access,
+ u32 *error)
{
struct guest_walker walker;
gpa_t gpa = UNMAPPED_GVA;
int r;
- r = FNAME(walk_addr)(&walker, vcpu, vaddr, 0, 0, 0);
+ r = FNAME(walk_addr)(&walker, vcpu, vaddr,
+ !!(access & PFERR_WRITE_MASK),
+ !!(access & PFERR_USER_MASK),
+ !!(access & PFERR_FETCH_MASK));
if (r) {
gpa = gfn_to_gpa(walker.gfn);
gpa |= vaddr & ~PAGE_MASK;
- }
+ } else if (error)
+ *error = walker.error_code;
return gpa;
}
static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
{
int i, offset, nr_present;
+ bool reset_host_protection;
+ gpa_t first_pte_gpa;
offset = nr_present = 0;
if (PTTYPE == 32)
offset = sp->role.quadrant << PT64_LEVEL_BITS;
+ first_pte_gpa = gfn_to_gpa(sp->gfn) + offset * sizeof(pt_element_t);
+
for (i = 0; i < PT64_ENT_PER_PAGE; i++) {
unsigned pte_access;
pt_element_t gpte;
if (!is_shadow_present_pte(sp->spt[i]))
continue;
- pte_gpa = gfn_to_gpa(sp->gfn);
- pte_gpa += (i+offset) * sizeof(pt_element_t);
+ pte_gpa = first_pte_gpa + i * sizeof(pt_element_t);
if (kvm_read_guest_atomic(vcpu->kvm, pte_gpa, &gpte,
sizeof(pt_element_t)))
nr_present++;
pte_access = sp->role.access & FNAME(gpte_access)(vcpu, gpte);
+ if (!(sp->spt[i] & SPTE_HOST_WRITEABLE)) {
+ pte_access &= ~ACC_WRITE_MASK;
+ reset_host_protection = 0;
+ } else {
+ reset_host_protection = 1;
+ }
set_spte(vcpu, &sp->spt[i], pte_access, 0, 0,
- is_dirty_gpte(gpte), 0, gfn,
- spte_to_pfn(sp->spt[i]), true, false);
+ is_dirty_gpte(gpte), PT_PAGE_TABLE_LEVEL, gfn,
+ spte_to_pfn(sp->spt[i]), true, false,
+ reset_host_protection);
}
return !nr_present;
#undef PT_BASE_ADDR_MASK
#undef PT_INDEX
#undef PT_LEVEL_MASK
-#undef PT_DIR_BASE_ADDR_MASK
+#undef PT_LVL_ADDR_MASK
+#undef PT_LVL_OFFSET_MASK
#undef PT_LEVEL_BITS
#undef PT_MAX_FULL_LEVELS
#undef gpte_to_gfn
-#undef gpte_to_gfn_pde
+#undef gpte_to_gfn_lvl
#undef CMPXCHG
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff